Skip to main content
SpringerLink
Log in

Methodology and Tools for Designing Binary Neural Networks

  • Published:
Programming and Computer Software Aims and scope Submit manuscript

Abstract

This paper presents results of a research in the field of software development, design methods, as well as training and synthesis of binary neural networks. The research is based on the model of a biomorphic neuron proposed by A.A. Zhdanov, which features noise immunity and is capable of forgetting and additional training. Software tools for designing and visualizing the modeling of binary neural structures are described. Use cases and features of a formal markup language for neural network models, as well as principles of generating deep learning structures, are discussed. A neural network markup language interpreter can automatically generate source code in Verilog with the description of the neural-like implementation of intelligent systems for software and hardware solutions on programmable logic devices (PLDs).

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.

Similar content being viewed by others

Notes

  1. An example is the explosive growth in neural network recognition technologies with the advent of specialized graphics accelerators in 2006.

REFERENCES

  1. Brewer, G.J., Boehler, M.D., Pearson, R.A., DeMaris, A.A., Ide, A.N., and Wheeler, B.C., Neuron network activity scales exponentially with synapse density, J. Neural Eng., 2008, vol. 6, no. 1. https://doi.org/10.1088/1741-2560/6/1/014001

  2. Zhdanov, A.A., Avtonomnyi iskusstvennyi intellekt (Autonomous Artificial Intelligence), Moscow: BINOM. Laboratoriya znanii, 2009, 2nd ed.

  3. Zhdanov, A.A., Kryzhanovskii, M.V., and Preobrazhenskii, N.B., Bionic intelligent adaptive control system for the mobile robot, Iskusstvennyi Intellekt, 2002, vol. 4, pp. 341–350.

    Google Scholar 

  4. Mishustin, I.A., Preobrazhenskii, N.B., Zhdanov, A.A., and Stepanyan, I.V., Hardware implementation of a neural-like network capable of recognizing noisy patterns, Neirokomp’yutery Razrab. Primen., 2018, no. 6, pp. 19–25.

  5. Stepanyan, I.V. and Ziep, N.N., Growing convolutional neural-like structures for static pattern recognition problems, Neirokomp’yutery Razrab. Primen., 2018, no. 5, pp. 4–11.

  6. Vella, M., Cannon, R.C., Crook, S., Davison, A.P., Ganapathy, G., Robinson, H.P., Silver, R.A., and Gleeson, P., libNeuroML and PyLEMS: Using Python to combine procedural and declarative modeling approaches in computational neuroscience, Front. Neuroinf., 2014, vol. 8, p. 38.

    Article  Google Scholar 

  7. Ponulak, F., Introduction to spiking neural networks: Information processing, learning and applications, Acta Neurobiol. Exp., 2010, vol. 71, pp. 409–433.

    Google Scholar 

  8. Maas, W., Networks of spiking neurons: The third generation of neural network models, Neural Networks, 1997, vol. 10, pp. 1659–1671. https://doi.org/10.1016/S0893-6080(97)00011-7

    Article  Google Scholar 

  9. Davies, M., Srinivasa, N., Lin, T.-H., Chinya, G., Cao, Y., Choday, S.H., Dimou, G., Joshi, P., Imam, N., Jain, S., Liao, Y., Lin, C.-K., Lines, A., Liu, R., Mathaikutty, D., McCoy, S., Paul, A., Tse, J., Venkataramanan, G., Weng, Y.-H., Wild, A., Yang, Y., and Wang, H., Loihi: A neuromorphic manycore processor with on-chip learning, IEEE Micro, 2018, vol. 38, no. 1, pp. 82–99. https://doi.org/10.1109/MM.2018.112130359

    Article  Google Scholar 

  10. Schmidhuber, J., Deep learning in neural networks: An overview, Neural Networks, 2015, vol. 61, pp. 85–117.

    Article  Google Scholar 

  11. LeCun, Y. and Bengio, Y., Convolutional networks for images, speech, and time-series, The Handbook of Brain Theory and Neural Networks, Arbib, M.A., Ed., MIT Press, 1995.

    Google Scholar 

  12. Dileep, G. and Jeff, H., Towards a mathematical theory of cortical micro-circuits, PLoS Comput. Biol., 2009, vol. 5, no. 10, p. E1000532.

    Article  MathSciNet  Google Scholar 

  13. Stepanyan, I.V., Lekomtsev, D.A., and Zhdanov, A.A., State Registration Certificate on PC Program no. 2016611299, Computer-aided design system for biomorphic neural networks Neurox, 2016.

  14. Zhdanov, A.A., Nguyen Ngoc Diep, Perskii, G.S., Peshenko, R.E., Pizhonkov, A.G., Stepanyan, I.V., and Syamiullin, Z.S., State Registration Certificate on PC Program no. 2018661458, A program for the dynamic synthesis of growing biosimilar structures based on artificial neurons with extended functionality and additional-training capability for pattern recognition and dynamic object control problems, 2018.

  15. Zhdanov, A.A., Peshenko, R.E., Pizhonkov, A.G., Smirnov, S.P., and Stepanyan, I.V., State Registration Certificate on PC Program no. 2018663628, A program for multilevel autonomous control (MAC) of dynamic objects based on artificial neurons with extended functionality and additional-training capability, 2018.

  16. Savel’ev, A.V., Neurocomputers in inventions, Neirokomp’yutery Razrab. Primen., 2004, nos. 2–3, pp. 33–49.

  17. Savel’ev, A.V., Neurosociometodology for the problem of dialogue between neurobiology and neuromodeling, Neirokomp’yutery Razrab. Primen., 2011, no. 1, pp. 47–63.

Download references

Author information

Authors and Affiliations

  1. Blagonravov Mechanical Engineering Research Institute, Russian Academy of Sciences, Malyi Khariton’evskii per. 4, 101000, Moscow, Russia

    I. V. Stepanyan

Authors
  1. I. V. Stepanyan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to I. V. Stepanyan.

Additional information

Translated by Yu. Kornienko

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Stepanyan, I.V. Methodology and Tools for Designing Binary Neural Networks. Program Comput Soft 46, 49–56 (2020). https://doi.org/10.1134/S0361768820010065

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S0361768820010065

Search

Navigation